introduction - yıldız teknik Üniversitesiyildiz.edu.tr/~tastan/teaching/01 introduction.pdf ·...

INTRODUCTION

Huseyin Tastan1

1Yıldız Technical UniversityDepartment of Economics

These presentation notes are based onIntroductory Econometrics: A Modern Approach (2nd ed.)

by J. Wooldridge.

14 Ekim 2012

Econometrics I: Introduction - H. Tastan 1

What is econometrics?

Literal meaning: economic measurement: “econo-metrics”.

But the scope of econometrics is much wider.

Two popular definitions of econometrics:

“Econometrics may be defined as the social science in whichthe tools of economic theory, mathematics, and statisticalinference are applied to the analysis of economic phenomena”.(A.S. Goldberger, 1964).

“...econometrics may be defined as the quantitative analysisof actual economic phenomena based on the concurrentdevelopment of theory and observation, related by appropriatemethods of science”. (P. Samuelson)

Scope of Econometrics

Developing statistical methods for the estimation of economicrelationships,

Testing economic theories and hypothesis,

Evaluating and applying economic policies,

Forecasting,

Collecting and analyzing nonexperimental or observationaldata.

Forecasting,

Components of Econometrics

Econometric inputs:

Economic TheoryMathematicsStatistical TheoryDataComputers (CPU power)Interpretation

Econometric outputs:

Estimation - MeasurementInference - Hypothesis testingForecasting - PredictionEvaluation

Econometric inputs:

Why Do We Need Econometrics?

We learned statistical methods so why do we need a separatediscipline?

The reason is as follows: econometrics focuses on the analysisof nonexperimental economic data.

Nonexperimental data (or observational data) are notobtained through controlled experiments on economic agents(consumers, firms, households, sectors, countries, etc.)

Experimental data are collected in laboratory environmentsin natural sciences.

Although some social experiments can be devised it is usuallyimpossible to conduct economic experiments.

Unlike statistical methods employed in natural sciences,econometrics develops special methods to handlenonexperimental data.

Classical Methodology in Econometrics

Formulation of theory or hypothesis,

Specification of economic (mathematical) model,

Specification of econometric model,

Collecting data,

Estimation of parameters,

Hypothesis tests,

Forecasting/Prediction),

Evaluation of results for policy analysis or decision making.(Gujarati, p.3)

Collecting data,

Hypothesis tests,

Collecting data,

Hypothesis tests,

Collecting data,

Hypothesis tests,

Collecting data,

Hypothesis tests,

Collecting data,

Hypothesis tests,

Collecting data,

Hypothesis tests,

Collecting data,

Hypothesis tests,

ECONOMIC MODEL

Example 1 - Economic Model of Crime

y = f(x1, x2, x3, x4, x5, x6, x7),

f functional form (not yet specified)

Description of variables

y: hours spent in criminal activities,

x1: “earnings” for an hour spent in criminal activity,

x2: hourly wage in legal employment,

x3: other income,

x4: probability of getting caught,

x5: probability of being convicted if caught,

x6: expected sentence if convicted,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL

y = f(x1, x2, x3, x4, x5, x6, x7),

x3: other income,

x7: age

ECONOMIC MODEL vs. ECONOMETRIC MODEL

Economic Model Example 2 - Job Training and WorkerProductivity

wage = f(educ, exper, training),

wage: hourly wage (in dollars)educ : level of education (in years)exper : level of workforce experience (in years)training : weeks spent in job training.

Econometric Model: f Linear specification

wage = β0 + β1educ+ β2exper + β3training + u

ECONOMIC MODEL vs. ECONOMETRIC MODEL

Economic Model Example 2 - Job Training and WorkerProductivity

wage = f(educ, exper, training),

wage: hourly wage (in dollars)educ : level of education (in years)exper : level of workforce experience (in years)training : weeks spent in job training.

Econometric Model: f Linear specification

ECONOMETRIC MODEL: Linear Specification

Econometric Model Example 2 - Job Training and WorkerProductivity

Components of econometric model:

u: random error term or disturbance term

Random error term u contains influence of factors that arenot included in the model. It also contains unobserved factorssuch as innate ability or family background.

No matter how comprehensive the specified model there willalways factors that cannot be included in the econometricmodel. We can never eliminate u entirely.

β0,β1,β2,β3: parameters of the econometric model

These are unknown constants.

They describe the directions and strengths of the relationshipbetween wage and factors affecting wage included in themodel.

For example, we may be interested in testing H0 : β3 = 0which says that job training has no effect on wage.

ECONOMETRIC DATA TYPES

Cross-sectional data

Time series data

Pooled cross-section

Panel data (longitudinal data)

Time series data

Cross-sectional data:

consists of a sample of individuals, households, firms, cities,states, countries, or a variety of other units, taken at a givenpoint in time

Significant feature: random sampling from a target population

Generally obtained through official records of individual units,surveys, questionnaires (data collection instrument thatcontains a series of questions designed for a specific purpose)

For example, household income, consumption andemployment surveys conducted by the Turkish StatisticalInstitute (TUIK/TURKSTAT)

Cross-sectional data example: Wage Data (GRETL dataset: wage1.gdt)

A Cross-sectional data set on wages and individual characteristics

Obs. No wage educ exper female married

1 3.10 11 2 1 02 3.24 12 22 1 13 3.00 11 2 0 04 6.00 8 44 0 15 5.30 12 7 0 16 8.75 16 9 0 1. . . . . .. . . . . .. . . . . .

524 4.67 15 13 0 1525 11.56 16 5 0 1526 3.50 14 5 1 0

Time series data:

consists of observations on a variable or several variables overtime.

Chronological ordering

Frequency of time series data: hour, day, week, month, year

Time length between observations is generally equal

Examples of time series data include stock prices, moneysupply, consumer price index, gross domestic product, annualhomicide rates, and automobile sales figures.

Time series data:

A Time Series Data Example: GRETL: prminwage.gdt

Pooled cross-section:

consists of cross-sectional data sets that are observed indifferent time periods and combined together

At each time period (e.g., year) a different random sample ischosen from population

Individual units are not the same

For example if we choose a random sample 400 firms in 2002and choose another sample in 2010 and combine thesecross-sectional data sets we obtain a pooled cross-section dataset.

Cross-sectional observations are pooled together over time.

A Pooled Cross-sectional Data Example

Panel Data (longitudinal data):

consists of a time series for each cross-sectional member inthe data set.

The same cross-sectional units (firms, households, etc.) arefollowed over time.

For example: wage, education, and employment history for aset of individuals followed over a ten-year period.

Another example: cross-country data set for a 20 year periodcontaining life expectancy, income inequality, real GDP percapita and other country characteristics.

A Panel Data Example

Causality and the Notion of Ceteris Paribus

In testing economic theory usually our goal is to infer that onevariable has a causal effect on another variable.

Correlation may be suggestive but cannot be used to infercausality.

Fundamental notion: Ceteris paribus: “other relevant factorsbeing equal”

Or “holding all other factors fixed”

Most economic questions are ceteris paribus by nature.

For example, in analyzing consumer demand, we are interestedin knowing the effect of changing the price of a good on itsquantity demanded, while holding all other factors (such asincome, prices of other goods, and individual tastes) fixed.

If other factors are not held fixed, then we cannot know thecausal effect of a price change on quantity demanded.

Therefore, the relevant question in econometric analysis is “dowe control sufficient number of factors?”

Are there other factors that are not included in the model?

Can we say that other components are held fixed?

In most serious applications the number of factors is immenseso the isolation of the effect of any particular variable mayseem hopeless. But, if properly used, econometric methodscan help us determine ceteris paribus effects.

Ceteris Paribus Example: Effects of Fertilizer on Crop Yield

Suppose the crop is wheat. We are interested in measuring theimpact of fertilizer on wheat yield (production).

Obviously there are several factors that affect the productionof wheat such as rainfall, quality of soil and presence ofparasites.

We need to control these factors in order to determine theceteris paribus impact of fertilizers.

To do this we can devise the following experiment: divide theland into equal pieces (such as one acre) and apply differentamounts of fertilizer to each land plot and then measure thewheat yield.

This gives us a cross-sectional data set where observation unitis land plot.

We can apply statistical methods to this data set to measurethe impact of fertilizers on crop yield.

Ceteris Paribus Example: Effects of Fertilizer on WheatYield

How do we know the results of this experiment can be used tomeasure the ceteris paribus effect of fertilizer?

Can we be sure that all other factors (quality of land plots forexample) are held fixed?

It is generally very difficult to observe the quality of soil.

But we can still use ceteris paribus notion

Amounts of fertilizers should be assigned to land plotsindependently of other plot features such as quality of plots

In other words, other characteristics of plots should be ignoredwhen deciding on fertilizer amounts.

Ceteris Paribus Example: Measuring the Return toEducation

Question: How can we measure the return to education?

If a person is chosen from the population and given anotheryear of education, by how much will his or her wage increase?

This is also a ceteris paribus question: all other factors are heldfixed while another year of education is given to the person.

There are several factors other than education that affectwages: experience, tenure, innate ability, gender, age, region,marital status, etc.

Example: Measuring the Return to Education

Similar to fertilizer example we can design the followinghypothetical experiment:Social planner has the ability to assign any level of eductionto any person.The planner chooses a group of individuals from populationand randomly assign each person an amount of education:some are given high school education, some are given 4-yearcollege education, etc.Subsequently the planner measures wages for each individual.If levels of education are assigned independently of othercharacteristics that affect productivity (such as innate abilityor experience) then we can measure the impact of educationon wages correctly.Of course such an experiment is impossible to conduct.Even though we cannot obtain an experimental data, we canobtain observational data set that contains information onwages, education, experience and other personalcharacteristics (e.g. from TUIK household employmentsurveys)

People choose their education levels. Thus, individualcharacteristics will be correlated with the level of education.

For example, people with more innate ability tend to havehigher levels of education.

Workers with higher levels of education tend to have higherwages.

It becomes difficult to isolate the impact of education fromthe impact of innate ability on wages.

How much of this effect comes from education? How muchfrom innate ability?

Ceteris Paribus Example: The Effect of Law Enforcementon City Crime Levels

Does the presence of more police officers on the street detercrime?

Ceteris paribus question: If a city is randomly chosen andgiven, say, ten additional police officers, by how much wouldits crime rates fall?

Or: If two cities are the same in all respects, except that cityA has ten more police officers than city B, by how muchwould the two cities’ crime rates differ?

It almost impossible to find two cities identical in all respects.

But this is not necessary in econometric analysis.

We just need to know if the data on crime rates and numberof police officers can be viewed as experimental.

In most cases this is not the case, data is observational.

The size of police force is determined by city authorities whoprobably take into account several other city characteristics.

The problem is a little bit more complex: Does the size ofpolice force affect the amount of crime or vice versa?

The amount of crime and police force are simultaneouslydetermined.

introduction - yıldız teknik Üniversitesiyildiz.edu.tr/~tastan/teaching/01 introduction.pdf ·...

Documents

advance econometrics

applied econometrics using matlab - econometrics toolbox for

econometrics paper

econometrics gretl

spatial econometrics - csiss · spatial econometrics luc...

Örnekleme - yıldız teknik...

machine learning 10601 recitation 8 oct 21, 2009 oznur...

statistics & econometrics statistics & econometrics...

econometrics hansen

simple regression model - yıldız teknik...

yildiz teknİk...

econometrics lecture

econometrics i - new york...

machine learning 10601 recitation 6 sep 30, 2009 oznur...

applied econometrics

econometrics note

msc econometrics & mathematical economics - study...

introductory econometrics - gargi college · introductory...

econometrics i - new york...

econometrics i - new york...